This notebook contains a set of analyses for analyzing Phil’s boardgamegeek collection. The bulk of the analysis is focused on building a user-specific predictive model to predict the games that the specified user is likely to own. This enables us to ask questions like, based on the games the user currently owns, what games are a good fit for their collection? What upcoming games are they likely to purchase?
We can look at a basic description of the number of games that the user owns, has rated, has previously owned, etc.
What years has the user owned/rated games from? While we can’t see when a user added or removed a game from their collection, we can look at their collection by the years in which their games were published.
We can look at the most frequent types of categories, mechanics, designers, and artists that appear in a user’s collection.
We’ll examine predictive models trained on a user’s collection for games published through 2020. How many games has the user owned/rated/played in the training set (games prior to 2020)?
username | dataset | period | games_owned | games_rated |
Phil | training | published before 2020 | 122 | 132 |
Phil | validation | published 2020 | 20 | 12 |
Phil | test | published after 2020 | 7 | 1 |
The main outcome we will be modeling for the user is owned, which refers to whether the user currently owns or has a previously owned a game in their collection. Our goal is to train a predictive model to learn the probability that a user will add a game to their collection based on its observable features. This amounts to looking at historical data and looking to find patterns that exist between features of games and games present in the user’s collection.
One of the models we trained was a decision tree, which looks for decision rules that can be used to separate games the user owns from games they don’t. The resulting model produces a decision corresponding to yes or no statements: to explain why the model predicts the user to own game, we start at the top of the tree and follow the rules that were learned from the training data.
Note: the tree below has been further pruned to make it easier to visualize.
Decision trees are highly interpretible models that are easy to train and can identify important interactions and nonlinearities present in the data. Individual trees have the drawback of being less predictive than other common models, but it can be useful to look at them to gain some understanding of key predictors and relationships found in the training data.
We can examine coefficients from another model we trained, which is a logistic regression with elastic net regularization (which I will refer to as a penalized logistic regression). Positive values indicate that a feature increases a user’s probability of owning/rating a game, while negative values indicate a feature decreases the probability. To be precise, the coefficients indicate the effect of a particular feature on the log-odds of a user owning a game.
Why did the model identify these features? We can make density plots of the important features for predicting whether the user owned a game. Blue indicates the density for games owned by the user, while grey indicates the density for games not owned by the user.
Binary predictors can be difficult to see with this visualization, so we can also directly examine the percentage of games in a user’s collection with a predictor vs the percentage of all games with that predictor.
% of Games with Feature | ||||
username | Feature | User_Collection | All_Games | Ratio |
Phil | Capstone Games | 4.1% | 0.1% | 36.84 |
Phil | Space Cowboys | 4.9% | 0.2% | 27.79 |
Phil | Fantasy Flight Games | 19.7% | 1.1% | 18.35 |
Phil | Asmodee | 32.0% | 2.5% | 12.87 |
Phil | Renegade Game Studios | 3.3% | 0.4% | 8.31 |
Phil | ZMan Games | 11.5% | 1.4% | 8.25 |
Phil | Map Continental National Scale | 14.8% | 1.9% | 7.86 |
Phil | Pegasus Spiele | 13.1% | 2.2% | 6.06 |
Phil | Murder Mystery | 7.4% | 1.5% | 5.01 |
Phil | Collectible Components | 6.6% | 1.7% | 3.76 |
Phil | Cryptozoic Entertainment | 1.6% | 0.5% | 3.41 |
Phil | France | 4.9% | 1.5% | 3.34 |
Phil | Deduction Game | 14.8% | 5.0% | 2.93 |
Phil | Food Cooking | 3.3% | 1.2% | 2.72 |
Phil | Fantasy | 13.9% | 11.9% | 1.17 |
Phil | Movement Points | 2.5% | 2.4% | 1.04 |
Before predicting games in upcoming years, we can examine how well the model did and what games it liked in the training set. In this case, we used resampling techniques (cross validation) to ensure that the model had not seen a game before making its predictions.
Displaying the 100 games from the training set with the highest probability of ownership, highlighting in blue games the user has owned.
Rank | Published | ID | Name | Pr(Owned) | Owned |
1 | 2013 | 143693 | Glass Road | 0.961 | no |
2 | 2017 | 233078 | Twilight Imperium: Fourth Edition | 0.938 | yes |
3 | 2018 | 205896 | Rising Sun | 0.931 | no |
4 | 2017 | 220308 | Gaia Project | 0.900 | no |
5 | 2016 | 205637 | Arkham Horror: The Card Game | 0.888 | yes |
6 | 2012 | 124742 | Android: Netrunner | 0.771 | no |
7 | 2014 | 164928 | Orléans | 0.743 | no |
8 | 2019 | 276025 | Maracaibo | 0.722 | yes |
9 | 2016 | 187645 | Star Wars: Rebellion | 0.716 | no |
10 | 2016 | 167791 | Terraforming Mars | 0.714 | no |
11 | 2015 | 175878 | 504 | 0.692 | no |
12 | 2017 | 174430 | Gloomhaven | 0.689 | yes |
13 | 2011 | 59959 | Letters from Whitechapel | 0.676 | yes |
14 | 2004 | 9609 | War of the Ring | 0.662 | no |
15 | 2016 | 176083 | Hit Z Road | 0.641 | no |
16 | 2014 | 145371 | Three Kingdoms Redux | 0.638 | no |
17 | 2017 | 221107 | Pandemic Legacy: Season 2 | 0.636 | no |
18 | 2019 | 270971 | Era: Medieval Age | 0.628 | no |
19 | 2015 | 170216 | Blood Rage | 0.609 | no |
20 | 2010 | 25292 | Merchants & Marauders | 0.590 | yes |
21 | 2019 | 266507 | Clank!: Legacy – Acquisitions Incorporated | 0.579 | no |
22 | 2019 | 281946 | Aftermath | 0.553 | no |
23 | 2017 | 162886 | Spirit Island | 0.548 | no |
24 | 2011 | 96848 | Mage Knight Board Game | 0.544 | no |
25 | 2015 | 181530 | Runebound (Third Edition) | 0.540 | no |
26 | 2008 | 37111 | Battlestar Galactica: The Board Game | 0.534 | no |
27 | 1999 | 552 | Bus | 0.507 | no |
28 | 2019 | 286096 | Tapestry | 0.499 | no |
29 | 2012 | 121921 | Robinson Crusoe: Adventures on the Cursed Island | 0.477 | no |
30 | 2019 | 253635 | Ragusa | 0.473 | no |
31 | 1999 | 54 | Tikal | 0.462 | no |
32 | 2017 | 232918 | Fallout | 0.450 | no |
33 | 1982 | 2511 | Sherlock Holmes Consulting Detective: The Thames Murders & Other Cases | 0.439 | yes |
34 | 2011 | 70919 | Takenoko | 0.439 | no |
35 | 2018 | 256226 | Azul: Stained Glass of Sintra | 0.421 | no |
36 | 2012 | 104162 | Descent: Journeys in the Dark (Second Edition) | 0.414 | no |
37 | 2000 | 478 | Citadels | 0.392 | no |
38 | 1997 | 42 | Tigris & Euphrates | 0.388 | no |
39 | 2019 | 269385 | The Lord of the Rings: Journeys in Middle-Earth | 0.386 | yes |
40 | 2016 | 205059 | Mansions of Madness: Second Edition | 0.374 | yes |
41 | 2012 | 123096 | Space Cadets | 0.372 | yes |
42 | 2008 | 33107 | Senji | 0.369 | no |
43 | 2010 | 62219 | Dominant Species | 0.366 | no |
44 | 2012 | 120677 | Terra Mystica | 0.358 | yes |
45 | 2018 | 244711 | Newton | 0.357 | no |
46 | 2018 | 257501 | KeyForge: Call of the Archons | 0.356 | yes |
47 | 2011 | 103343 | A Game of Thrones: The Board Game (Second Edition) | 0.352 | no |
48 | 2019 | 271896 | Star Wars: Outer Rim | 0.350 | no |
49 | 2017 | 220775 | Codenames: Disney – Family Edition | 0.350 | no |
50 | 2019 | 253344 | Cthulhu: Death May Die | 0.343 | no |
51 | 2019 | 285774 | Marvel Champions: The Card Game | 0.342 | yes |
52 | 2014 | 148228 | Splendor | 0.337 | no |
53 | 2017 | 234671 | Pandemic: Rising Tide | 0.326 | no |
54 | 2013 | 127024 | Room 25 | 0.321 | no |
55 | 2015 | 181304 | Mysterium | 0.312 | no |
56 | 2017 | 184151 | Legend of the Five Rings: The Card Game | 0.298 | no |
57 | 2018 | 246297 | Shadows: Amsterdam | 0.297 | no |
58 | 1998 | 3 | Samurai | 0.293 | no |
59 | 2018 | 260428 | Pandemic: Fall of Rome | 0.293 | yes |
60 | 2008 | 38159 | Ultimate Werewolf: Ultimate Edition | 0.292 | no |
61 | 2009 | 43868 | The Adventurers: The Temple of Chac | 0.291 | no |
62 | 2015 | 172386 | Mombasa | 0.285 | no |
63 | 2018 | 209324 | The World of SMOG: Rise of Moloch | 0.284 | no |
64 | 2010 | 73171 | Earth Reborn | 0.284 | no |
65 | 2017 | 188920 | This War of Mine: The Board Game | 0.280 | no |
66 | 1999 | 88 | Torres | 0.280 | no |
67 | 2019 | 274364 | Watergate | 0.257 | yes |
68 | 2017 | 238065 | Sherlock Holmes Consulting Detective: Vanishing from Hyde Park | 0.250 | no |
69 | 2017 | 234487 | Altiplano | 0.239 | no |
70 | 2018 | 313010 | Cosmic Encounter: 42nd Anniversary Edition | 0.236 | no |
71 | 2008 | 30549 | Pandemic | 0.235 | no |
72 | 2015 | 146508 | T.I.M.E Stories | 0.234 | no |
73 | 2019 | 253574 | Crusader Kings | 0.231 | no |
74 | 2017 | 224037 | Codenames: Duet | 0.229 | no |
75 | 2003 | 6472 | A Game of Thrones | 0.227 | no |
76 | 1995 | 112 | Condottiere | 0.226 | no |
77 | 2010 | 73439 | Troyes | 0.225 | yes |
78 | 2004 | 10547 | Betrayal at House on the Hill | 0.225 | no |
79 | 2008 | 38453 | Space Alert | 0.225 | no |
80 | 2014 | 161882 | Irish Gauge | 0.223 | yes |
81 | 2014 | 157403 | Black Fleet | 0.219 | no |
82 | 2012 | 127023 | Kemet | 0.217 | yes |
83 | 2018 | 252328 | Star Wars: X-Wing (Second Edition) | 0.216 | yes |
84 | 2016 | 169786 | Scythe | 0.215 | no |
85 | 2018 | 222509 | Lords of Hellas | 0.215 | no |
86 | 2018 | 257499 | Arkham Horror (Third Edition) | 0.212 | no |
87 | 2011 | 42776 | Gears of War: The Board Game | 0.209 | no |
88 | 2012 | 104710 | Wiz-War (Eighth Edition) | 0.201 | no |
89 | 2009 | 39683 | At the Gates of Loyang | 0.194 | no |
90 | 2012 | 119391 | Il Vecchio | 0.193 | no |
91 | 2004 | 9440 | Maharaja: The Game of Palace Building in India | 0.192 | no |
92 | 2015 | 182694 | Watson & Holmes | 0.191 | yes |
93 | 2006 | 14808 | Marvel Heroes | 0.190 | no |
94 | 2005 | 12493 | Twilight Imperium: Third Edition | 0.189 | yes |
95 | 2010 | 77130 | Sid Meier's Civilization: The Board Game | 0.189 | no |
96 | 2009 | 54043 | Jaipur | 0.188 | no |
97 | 2016 | 198773 | Codenames: Pictures | 0.187 | no |
98 | 2006 | 21882 | Blue Moon City | 0.186 | no |
99 | 2011 | 83330 | Mansions of Madness | 0.185 | no |
100 | 2016 | 171131 | Captain Sonar | 0.185 | no |
This section contains a variety of visualizations and metrics for assessing the performance of the model(s) during resampling. If you’re not particularly interested in predictive modeling, skip down further to the predictions from the model.
An easy way to examine the performance of classification model is to view a separation plot. We plot the predicted probabilities from the model for every game (from resampling) from lowest to highest. We then overlay a blue line for any game that the user does own. A good classifier is one that is able to separate the blue (games owned by the user) from the white (games not owned by the user), with most of the blue occurring at the highest probabilities (right side of the chart).
We can more formally assess how well each model did in resampling by looking at the area under the receiver operating characteristic curve. A perfect model would receive a score of 1, while a model that cannot predict the outcome will default to a score of 0.5. The extent to which something is a good score depends on the setting, but generally anything in the .8 to .9 range is very good while the .7 to .8 range is perfectly acceptable.
wflow_id | .metric | .estimator | .estimate |
GLM | roc_auc | binary | 0.93 |
Decision Tree | roc_auc | binary | 0.77 |
Another way to think about the model performance is to view its lift, or its ability to detect the positive outcomes over that of a null model. High lift indicates the model can much more quickly find all of the positive outcomes (in this case, games owned or played by the user), while a model with no lift is no better than random guessing. A gains chart is another way to view this.
While we are probably more interested in the lift provided by the models to evaluate their efficacy, we can also explore the optimal cutpoint if we wanted to define a hard threshold for identifying games a user will own vs not own.
The threshold we select depends on how we much we care about false positives (games the model predicts that the user does not own) vs false negatives (games the user owns that the model does not predict). We can toggle threshold to
Finally, we can understand the performance of the model by examining its calibration. If the model assigns a probability of 5%, how often does the outcome actually occur? A well calibrated model is one in which the predicted probabilities reflect the probabilities we would observe in the actual data. We can assess the calibration of a model by grouping its predictions into bins and assessing how often we observe the outcome versus how often our model expects to observe the outcome.
A model that is well calibrated will closely follow the dashed line - its expected probabilities match that of the observed probabilities. A model that consistently underestimates the probability of the event will be over this dashed line, be a while a model that overestimates the probability will be under the dashed line.
What games does the model think Phil is most likely to own that are not in their collection?
Published | ID | Name | Pr(Owned) | Owned |
2013 | 143693 | Glass Road | 0.961 | no |
2018 | 205896 | Rising Sun | 0.931 | no |
2017 | 220308 | Gaia Project | 0.900 | no |
2012 | 124742 | Android: Netrunner | 0.771 | no |
2014 | 164928 | Orléans | 0.743 | no |
What games does the model think Phil is least likely to own that are in their collection?
Published | ID | Name | Pr(Owned) | Owned |
1876 | 521 | Crokinole | 0.001 | yes |
2019 | 247367 | Air, Land, & Sea | 0.001 | yes |
2018 | 244521 | The Quacks of Quedlinburg | 0.002 | yes |
2016 | 203417 | Exit: The Game – The Secret Lab | 0.002 | yes |
2016 | 175640 | Vinhos Deluxe Edition | 0.002 | yes |
Top 25 games most likely to be owned by the user in each year, highlighting in blue the games that the user has owned.
rank | 2012 | 2013 | 2014 | 2015 | 2016 | 2017 | 2018 | 2019 |
1 | Android: Netrunner | Glass Road | Orléans | 504 | Arkham Horror: The Card Game | Twilight Imperium: Fourth Edition | Rising Sun | Maracaibo |
2 | Robinson Crusoe: Adventures on the Cursed Island | Room 25 | Three Kingdoms Redux | Blood Rage | Star Wars: Rebellion | Gaia Project | Azul: Stained Glass of Sintra | Era: Medieval Age |
3 | Descent: Journeys in the Dark (Second Edition) | Tash-Kalar: Arena of Legends | Splendor | Runebound (Third Edition) | Terraforming Mars | Gloomhaven | Newton | Clank!: Legacy – Acquisitions Incorporated |
4 | Space Cadets | Crossing | Irish Gauge | Mysterium | Hit Z Road | Pandemic Legacy: Season 2 | KeyForge: Call of the Archons | Aftermath |
5 | Terra Mystica | Coal Baron | Black Fleet | Mombasa | Mansions of Madness: Second Edition | Spirit Island | Shadows: Amsterdam | Tapestry |
6 | Kemet | Impulse | Ultimate Werewolf | T.I.M.E Stories | Scythe | Fallout | Pandemic: Fall of Rome | Ragusa |
7 | Wiz-War (Eighth Edition) | Bruxelles 1893 | Arkwright | Watson & Holmes | Codenames: Pictures | Codenames: Disney – Family Edition | The World of SMOG: Rise of Moloch | The Lord of the Rings: Journeys in Middle-Earth |
8 | Il Vecchio | Wildcatters | AquaSphere | A Game of Thrones: The Card Game (Second Edition) | Captain Sonar | Pandemic: Rising Tide | Cosmic Encounter: 42nd Anniversary Edition | Star Wars: Outer Rim |
9 | Love Letter | Lewis & Clark: The Expedition | Patchwork | Fury of Dracula (Third/Fourth Edition) | Citadels | Legend of the Five Rings: The Card Game | Star Wars: X-Wing (Second Edition) | Cthulhu: Death May Die |
10 | Merchant of Venus (Second Edition) | BANG! The Dice Game | Fields of Arle | Haspelknecht: The Story of Early Coal Mining | Black Orchestra | This War of Mine: The Board Game | Lords of Hellas | Marvel Champions: The Card Game |
11 | Keyflower | Eldritch Horror | Warhammer 40,000: Conquest | Risk: Europe | New Angeles | Sherlock Holmes Consulting Detective: Vanishing from Hyde Park | Arkham Horror (Third Edition) | Watergate |
12 | Rex: Final Days of an Empire | Concordia | Star Wars: Imperial Assault | Elysium | Star Wars: Destiny | Altiplano | Narcos: The Board Game | Crusader Kings |
13 | Archipelago | 1775: Rebellion | DungeonQuest Revised Edition | The Voyages of Marco Polo | Sherlock Holmes Consulting Detective: Jack the Ripper & West End Adventures | Codenames: Duet | Heroes of Terrinoth | Last Bastion |
14 | Zombicide | Cappuccino | King of New York | Star Wars: Armada | Pandemic: Iberia | Carthago: Merchants & Guilds | Coimbra | Black Angel |
15 | Star Wars: X-Wing Miniatures Game | Petits meurtres & faits divers: au tribunal | Akrotiri | Forbidden Stars | Covert | 878 Vikings: Invasions of England | Ultimate Werewolf Legacy | TIME Stories Revolution: Damien 1958 NT |
16 | Mafia: Vendetta | Forbidden Desert | Imperial Settlers | Arboretum | Coal Baron: The Great Card Game | Heaven & Ale | Unlock!: Escape Adventures – In Pursuit of Cabrakan | Machi Koro Legacy |
17 | Clash of Cultures | Patchistory | Deus | Exploding Kittens | Game of Thrones: The Iron Throne | Whitehall Mystery | Cosmic Run: Regeneration | Unlock!: Timeless Adventures |
18 | The Palaces of Carrara | Amerigo | Colt Express | Porta Nigra | Inis | Azul | The Estates | Yukon Airways |
19 | Polis: Fight for the Hegemony | Warhammer: Diskwars | Pandemic: The Cure | One Night Ultimate Vampire | Pandemic: Reign of Cthulhu | Unlock!: Escape Adventures – Temple of Ra | Concordia Venus | Unlock!: Epic Adventures |
20 | Winter Tales | Train Heist | Shipwrights of the North Sea | FUSE | Beyond Baker Street | Breaking Bad: The Board Game | Spy Club | Unlock!: Exotic Adventures – Expedition: Challenger |
21 | Libertalia | Relic | Arcadia Quest | Mission: Red Planet (Second Edition) | A Feast for Odin | Unlock!: Escape Adventures – The Elite | Book of Dragons | Caylus 1303 |
22 | Mutant Meeples | Pizza Party | Roll for the Galaxy | Star Realms: Colony Wars | Clank!: A Deck-Building Adventure | Unlock!: Escape Adventures – Fifth Avenue | Crusaders: Thy Will Be Done | Tainted Grail: The Fall of Avalon |
23 | Pax Porfiriana | Legacy: The Testament of Duke de Crecy | Castles of Mad King Ludwig | Bastion | Explorers of the North Sea | Sherlock Holmes Consulting Detective: Carlton House & Queen's Park | Reykholt | Hellenica: Story of Greece |
24 | Legends of Andor | Sanssouci | Five Tribes | Raiders of the North Sea | The Oracle of Delphi | Wendake | Unlock!: Heroic Adventures | Crystal Palace |
25 | Seasons | Zombicide Season 2: Prison Outbreak | Camel Up | Warhammer Quest: The Adventure Card Game | Agricola (Revised Edition) | The Godfather: Corleone's Empire | Renegade | Unmatched Game System |
This is an interactive table for the model’s predictions for the training set (from resampling).
We’ll validate the model by looking at its predictions for games published in 2020. That is, how well did a model trained on a user’s collection through 2020 perform in predicting games for the user in 2020?
username | outcome | dataset | method | .metric | .estimate |
Phil | owned | validation | GLM | roc_auc | 0.904 |
Phil | owned | validation | Decision Tree | roc_auc | 0.641 |
Table of top 50 games from 2020, highlighting games that the user owns.
Published | ID | Name | Pr(Owned) | Owned |
2020 | 291457 | Gloomhaven: Jaws of the Lion | 0.506 | yes |
2020 | 314040 | Pandemic Legacy: Season 0 | 0.373 | no |
2020 | 300001 | Renature | 0.284 | no |
2020 | 298572 | Cosmic Encounter Duel | 0.244 | no |
2020 | 296345 | Sherlock Holmes Consulting Detective: The Baker Street Irregulars | 0.232 | yes |
2020 | 256317 | Guild Master | 0.219 | no |
2020 | 300322 | Hallertau | 0.217 | no |
2020 | 246900 | Eclipse: Second Dawn for the Galaxy | 0.166 | no |
2020 | 296151 | Viscounts of the West Kingdom | 0.155 | no |
2020 | 302425 | Unlock!: Mythic Adventures | 0.142 | no |
2020 | 292333 | Cowboys II: Cowboys & Indians Edition | 0.138 | no |
2020 | 271524 | TIME Stories Revolution: A Midsummer Night | 0.125 | no |
2020 | 287742 | TIME Stories Revolution: The Hadal Project | 0.117 | no |
2020 | 312267 | Star Wars: Unlock! | 0.107 | no |
2020 | 301880 | Raiders of Scythia | 0.104 | no |
2020 | 300877 | New York Zoo | 0.104 | yes |
2020 | 316554 | Dune: Imperium | 0.103 | no |
2020 | 327913 | Unlock!: Timeless Adventures – Arsène Lupin und der große weiße Diamant | 0.090 | no |
2020 | 301767 | Mysterium Park | 0.067 | no |
2020 | 184267 | On Mars | 0.064 | yes |
2020 | 294788 | Conqueror: Final Conquest | 0.062 | no |
2020 | 293889 | Fallout Shelter: The Board Game | 0.060 | no |
2020 | 294484 | Unmatched: Cobble & Fog | 0.059 | yes |
2020 | 301919 | Pandemic: Hot Zone – North America | 0.059 | no |
2020 | 304285 | Infinity Gauntlet: A Love Letter Game | 0.058 | no |
2020 | 315060 | Unmatched: Buffy the Vampire Slayer | 0.053 | no |
2020 | 306481 | Tawantinsuyu: The Inca Empire | 0.052 | no |
2020 | 299592 | Beez | 0.052 | no |
2020 | 295905 | Cosmic Frog | 0.049 | no |
2020 | 318084 | Furnace | 0.046 | no |
2020 | 279537 | The Search for Planet X | 0.046 | yes |
2020 | 302809 | Betrayal at Mystery Mansion | 0.044 | no |
2020 | 325635 | Unmatched: Little Red Riding Hood vs. Beowulf | 0.044 | no |
2020 | 308652 | Age of Dogfights: WW1 | 0.042 | no |
2020 | 286749 | Hansa Teutonica: Big Box | 0.040 | yes |
2020 | 302465 | Obsidia | 0.040 | no |
2020 | 319966 | The King Is Dead: Second Edition | 0.040 | yes |
2020 | 284777 | Unmatched: Jurassic Park – InGen vs Raptors | 0.039 | yes |
2020 | 299179 | Chancellorsville 1863 | 0.038 | no |
2020 | 293296 | Splendor: Marvel | 0.037 | no |
2020 | 294235 | Crime Zoom: His Last Card | 0.037 | no |
2020 | 321305 | Crime Zoom: Bird of Ill Omen | 0.037 | no |
2020 | 321306 | Crime Zoom: A Deadly Writer | 0.037 | no |
2020 | 304420 | Bonfire | 0.036 | no |
2020 | 320819 | Dinner in Paris | 0.035 | no |
2020 | 301716 | Glasgow | 0.034 | no |
2020 | 297486 | Ride the Rails | 0.034 | no |
2020 | 312251 | Curious Cargo | 0.033 | no |
2020 | 318183 | Prehistories | 0.033 | no |
2020 | 299074 | Space Battle Lunchtime Card Game | 0.033 | no |
We can then refit our model to the training and validation set in order to predict all upcoming games for the user.
Examine the top 100 upcoming games, highlighting in blue ones the user already owns.
Rank | Published | ID | Name | Pr(Owned) | Owned |
1 | 2021 | 343905 | Boonlake | 0.746 | yes |
2 | 2022 | 349067 | The Lord of the Rings: The Card Game – Revised Core Set | 0.683 | no |
3 | 2022 | 331106 | The Witcher: Old World | 0.569 | no |
4 | 2021 | 339484 | Savannah Park | 0.433 | no |
5 | 2021 | 340466 | Unfathomable | 0.400 | yes |
6 | 2022 | 310873 | Carnegie | 0.398 | no |
7 | 2021 | 285967 | Ankh: Gods of Egypt | 0.325 | yes |
8 | 2021 | 344277 | Corrosion | 0.322 | no |
9 | 2022 | 256680 | Return to Dark Tower | 0.259 | no |
10 | 2023 | 347909 | Rogue Angels: Legacy of the Burning Suns | 0.258 | no |
11 | 2022 | 317511 | Tindaya | 0.253 | no |
12 | 2021 | 342942 | Ark Nova | 0.220 | yes |
13 | 2022 | 295770 | Frosthaven | 0.185 | no |
14 | 2021 | 339906 | The Hunger | 0.156 | no |
15 | 2021 | 291859 | Riftforce | 0.146 | yes |
16 | 2021 | 338980 | Eastern Empires | 0.121 | no |
17 | 2021 | 249277 | Brazil: Imperial | 0.114 | no |
18 | 2023 | 349793 | Age of Rome | 0.114 | no |
19 | 2021 | 298102 | Roll Camera!: The Filmmaking Board Game | 0.113 | no |
20 | 2022 | 322524 | Bardsung | 0.107 | no |
21 | 2022 | 326933 | Unmatched: Redemption Row | 0.105 | no |
22 | 2022 | 326934 | Unmatched: Hell's Kitchen | 0.105 | no |
23 | 2022 | 346199 | A Game of Thrones: B'Twixt | 0.104 | no |
24 | 2022 | 335764 | Unmatched: Battle of Legends, Volume Two | 0.103 | no |
25 | 2022 | 341945 | La Granja: Deluxe Master Set | 0.102 | no |
26 | 2022 | 326945 | Castles of Mad King Ludwig: Collector's Edition | 0.092 | no |
27 | 2021 | 299255 | Vienna Connection | 0.086 | no |
28 | 2021 | 324957 | The Snallygaster Situation: Kids on Bikes Board Game | 0.085 | no |
29 | 2021 | 304985 | Dark Ages: Holy Roman Empire | 0.083 | no |
30 | 2021 | 295535 | Dark Ages: Heritage of Charlemagne | 0.083 | no |
31 | 2021 | 291572 | Oath: Chronicles of Empire and Exile | 0.081 | no |
32 | 2021 | 338760 | Imperial Steam | 0.079 | no |
33 | 2021 | 330084 | Unlock!: Legendary Adventures | 0.079 | no |
34 | 2022 | 284778 | Unmatched: Jurassic Park – Dr. Sattler vs. T. Rex | 0.077 | no |
35 | 2021 | 311920 | Ultimate Werewolf: Extreme | 0.077 | no |
36 | 2021 | 342848 | World of Warcraft: Wrath of the Lich King | 0.072 | no |
37 | 2022 | 322656 | burncycle | 0.072 | no |
38 | 2021 | 340237 | Wonder Book | 0.070 | no |
39 | 2021 | 338834 | MicroMacro: Crime City – Full House | 0.067 | no |
40 | 2022 | 273814 | Deliverance | 0.065 | no |
41 | 2022 | 283137 | Human Punishment: The Beginning | 0.062 | no |
42 | 2021 | 331635 | Kameloot | 0.062 | no |
43 | 2021 | 326804 | Rorschach | 0.061 | no |
44 | 2022 | 315610 | Massive Darkness 2: Hellscape | 0.061 | no |
45 | 2022 | 305096 | Endless Winter: Paleoamericans | 0.059 | no |
46 | 2022 | 352263 | Through Ice and Snow | 0.059 | no |
47 | 2021 | 314491 | Meadow | 0.057 | no |
48 | 2021 | 322708 | Descent: Legends of the Dark | 0.056 | no |
49 | 2021 | 325698 | Juicy Fruits | 0.055 | no |
50 | 2021 | 295947 | Cascadia | 0.055 | no |
51 | 2021 | 339905 | Love Letter: Princess Princess Ever After | 0.055 | no |
52 | 2021 | 325022 | Coffee Traders | 0.055 | no |
53 | 2022 | 319807 | Shogun no Katana | 0.054 | no |
54 | 2021 | 333553 | For the King (and Me) | 0.052 | no |
55 | 2021 | 262201 | Sword & Sorcery: Ancient Chronicles | 0.051 | no |
56 | 2021 | 298069 | Cubitos | 0.050 | no |
57 | 2021 | 339789 | Welcome to the Moon | 0.048 | no |
58 | 2022 | 251661 | Oathsworn: Into the Deepwood | 0.047 | no |
59 | 2021 | 290236 | Canvas | 0.047 | no |
60 | 2021 | 273330 | Bloodborne: The Board Game | 0.047 | no |
61 | 2022 | 240980 | Blood on the Clocktower | 0.046 | no |
62 | 2021 | 306202 | Philosophia: Floating World | 0.045 | no |
63 | 2023 | 312959 | Rallyman: DIRT | 0.045 | no |
64 | 2021 | 319792 | Fly-A-Way | 0.044 | no |
65 | 2021 | 340909 | Gloomholdin' | 0.043 | no |
66 | 2022 | 266064 | Trudvang Legends | 0.043 | no |
67 | 2022 | 350316 | Wayfarers of the South Tigris | 0.043 | no |
68 | 2021 | 307862 | Dollars to Donuts | 0.042 | no |
69 | 2021 | 340834 | Gravwell: 2nd Edition | 0.041 | no |
70 | 2021 | 286751 | Zombicide: 2nd Edition | 0.041 | no |
71 | 2022 | 357746 | Disney Sorcerer's Arena: Epic Alliances Core Set | 0.040 | no |
72 | 2021 | 259962 | Stress Botics | 0.039 | no |
73 | 2022 | 325348 | Successors (Fourth Edition) | 0.038 | no |
74 | 2021 | 345435 | Fireball Island: Race to Adventure | 0.038 | no |
75 | 2022 | 338067 | 6: Siege – The Board Game | 0.038 | no |
76 | 2021 | 309319 | Apogee | 0.038 | no |
77 | 2021 | 298383 | Golem | 0.038 | no |
78 | 2022 | 353470 | Star Wars: Jabba's Palace – A Love Letter Game | 0.037 | no |
79 | 2021 | 329670 | Pandemic: Hot Zone – Europe | 0.037 | no |
80 | 2021 | 350636 | Unlock!: Game Adventures | 0.036 | no |
81 | 2022 | 353905 | Bureau of Investigation: Investigations in Arkham & Elsewhere | 0.035 | no |
82 | 2021 | 313730 | Harsh Shadows | 0.035 | no |
83 | 2021 | 334782 | Bayou Bash | 0.035 | no |
84 | 2021 | 303954 | Pax Viking | 0.034 | no |
85 | 2021 | 340455 | King of the Valley | 0.034 | no |
86 | 2021 | 304783 | Hadrian's Wall | 0.034 | no |
87 | 2021 | 260524 | Beyond Humanity: Colonies | 0.034 | no |
88 | 2021 | 346965 | Azul: Queen's Garden | 0.034 | no |
89 | 2021 | 347137 | Chronicles of Avel | 0.033 | no |
90 | 2021 | 341169 | Great Western Trail (Second Edition) | 0.033 | no |
91 | 2021 | 298378 | Maharaja | 0.033 | no |
92 | 2021 | 319899 | Decktective: Nightmare in the Mirror | 0.033 | no |
93 | 2021 | 292375 | The Great Wall | 0.033 | no |
94 | 2021 | 315937 | X-Men: Mutant Insurrection | 0.033 | no |
95 | 2021 | 336195 | League of Dungeoneers | 0.033 | no |
96 | 2022 | 311988 | Frostpunk: The Board Game | 0.032 | no |
97 | 2022 | 300217 | Merchants of the Dark Road | 0.032 | no |
98 | 2021 | 324242 | Sheepy Time | 0.032 | no |
99 | 2021 | 308989 | Bristol 1350 | 0.032 | no |
100 | 2022 | 347013 | Get on Board: New York & London | 0.031 | no |